Skip to main content

NE503 Verified Apps

The apps below are verified on real NE503 hardware and can be downloaded for testing.

For models, see the CamThink Model Zoo; this page provides verified app packages.

App List​

AppScenarioInference ModelPreviewVerification ResultDownload
Person DetectionPerimeter intrusion / area intrusion detectionhailo_yolov8n_384_640
Person Detection: app detailPerson Detection: running statusPerson Detection: detection result
Continuously detected 3 persons · 4.26M+ frames · ✅ Passedapp.yaml
image.tar
Occupancy MonitorArea people counting + occupancy monitoringhailo_yolov8n_384_640
Occupancy Monitor: app detailOccupancy Monitor: app statusOccupancy Monitor: detection result
Occupancy rate published periodically · frames 50→550 · ✅ Passedapp.yaml
image.tar
Safety Helmet DetectionConstruction safety PPE compliance — helmet / no-helmet detection with real-time alertssafety_helmet_yolov8n_384_640
Safety Helmet Detection: app statusSafety Helmet Detection: live detectionSafety Helmet Detection: detection result
Live detection of 9 persons (6 helmet + 3 no-helmet) · ✅ Passedapp.yaml
image.tar

Deployment​

After downloading app.yaml and image.tar, deploy through the Web Console:

Open Web Console → App Management → Import → Upload Package, upload app.yaml and image.tar separately, then click Install. After installation, click Start to launch the app.

Deploy app: upload app.yaml and image.tar

Model preloading required

Before first use, load the required model in Web Console Model Management:

  • Person Detection / Occupancy Monitor: scan and load the preinstalled hailo_yolov8n_384_640.
  • Safety Helmet Detection: import and load safety_helmet_yolov8n_384_640 HEF; the app package does not include the model.

Model preload: scan and load model

More app use cases are being adapted. For custom app development material, see Resources.